Skip to main content
Back to all work

Utility Drawing Symbol Detection

Two-stage YOLOv8 vision pipeline that finds every legend symbol across dense utility drawings.

  • YOLOv8
  • OpenCV
  • EasyOCR
  • Streamlit

The challenge

Engineers hunt for every legend symbol across dense, multi-page utility drawings by hand. A single full-page detector throws too many false positives to trust.

What we built

A vision pipeline converts PDFs to high-res images, then runs YOLOv8 in two stages: first find the legend table, then pull each symbol inside it. EasyOCR and Tesseract label the symbols, and multi-scale template matching marks every occurrence on the map pages. It all runs in a Streamlit app, GPU-accelerated via Docker on RunPod.

The result

Upload a PDF, download color-coded marked maps and a duplicate-legend report, nothing to install. The two-stage approach is far more reliable than a single pass.

Describe your project

A sentence or two. We'll take it from there.